THRD
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
new Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination. Existing defenses either rely on costly retraining -- often degrading model utility -- or apply single-turn analysis independently at each turn, failing to capture how risk accumulates along interaction trajectories. We observe that safety behavior in multi-turn interaction is trajectory-dependent: dialogue history continuously...